LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

GLM 5.3 vs Kimi K2.7 Code

Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace GLM 5.3 Replace Kimi K2.7 Code
GLM 5.3Z.ai
Coding
73.1
Overall
44.8
Output $/M
$1.40
36
Kimi K2.7 CodeMoonshot AI
Coding
39.1
Overall
25.8
Output $/M
$3.35
4
vs boards won of 40 shared

Decision reading

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 39.1 for Kimi K2.7 Code.

Pick Kimi K2.7 Code when a solved task costs $0.35 against $0.36, or when what matters is LiveCodeBench (Vals AI) or SkillsBench (Vals AI), where it leads.

Model AGLM 5.3Z.ai73.1/1002 independent benchmarks$0.36 per solved taskModel BKimi K2.7 CodeMoonshot AI39.1/1001 independent benchmark$0.35 per solved task
Shared results
40
GLM 5.3 only
60
Kimi K2.7 Code only
11
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GLM 5.3 73.1 from 2 benchmarks, Kimi K2.7 Code 39.1 from 1 benchmark.
Widest category
Agentic work, 15.1 points apart on average over 6 shared benchmarks.
Widest single gap
AA Agentic Index: GLM 5.3 53.1 against Kimi K2.7 Code 21.0, 32.1 points apart on a 0 to 100 scale.
Output price
GLM 5.3 $1.40 against Kimi K2.7 Code $3.35 per million output tokens, 2.4x apart.
Context window
GLM 5.3 takes 1.05M tokens, Kimi K2.7 Code 262K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGLM 5.3BarsKimi K2.7 CodeTies
Coding132
Intelligence20
Agentic work51
Reasoning40
Math21
Knowledge10
Web design80
General10
All shared boards364
CodingLike-for-likeFour of these boards feed the Vibe Coding Index132
Coding benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
LiveBench coding82.8%Not measuredOnly GLM 5.3 measured
LMArena WebDev16211474GLM 5.3
AA Coding Index74.860.8GLM 5.3
LiveCodeBench (Vals AI)80.5%82.0%Kimi K2.7 Code
SWE-bench Verified (Vals AI)95.4%78.2%GLM 5.3
Terminal-Bench 4 (Vals AI)38.9%Not measuredOnly GLM 5.3 measured
Vibe Code Bench (Vals AI)78.1%47.2%GLM 5.3
Code migration (Vals AI)44.2%25.4%GLM 5.3
ProgramBench (Vals AI)1.5%0.0%GLM 5.3
IOI (Vals AI)68.4%Not measuredOnly GLM 5.3 measured
Terminal-Bench 2.1 (Vals AI)71.5%67.0%GLM 5.3
Vibe Code Bench 1-100 (Vals AI)20.0%Not measuredOnly GLM 5.3 measured
SkillsBench (Vals AI)47.5%50.0%Kimi K2.7 Code
CyberBench (Vals AI)72.1%Not measuredOnly GLM 5.3 measured
SciCode59.0%47.8%GLM 5.3
Terminal-Bench Hard (Artificial Analysis run)Not measured44.7%Only Kimi K2.7 Code measured
FrontierCode40.1%30.1%GLM 5.3
FrontierSWE30.2%Not measuredOnly GLM 5.3 measured
WeirdML75.4%54.1%GLM 5.3
ALE-Bench1317.4886.2GLM 5.3
LMArena Text: coding1497Not measuredOnly GLM 5.3 measured
LMArena Text: software and IT1493Not measuredOnly GLM 5.3 measured
LMArena WebDev: React16411475GLM 5.3
LMArena WebDev: HTML15951451GLM 5.3
LMArena WebDev: from an imageNot measured1513Only Kimi K2.7 Code measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
AA Intelligence Index44.825.8GLM 5.3
Epoch Capabilities Index156.0150.1GLM 5.3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
Agentic work benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
AA Agentic Index53.121.0GLM 5.3
Design Arena: agents building web appsNot measured1176Only Kimi K2.7 Code measured
Design Arena: agents building full-stack appsNot measured1175Only Kimi K2.7 Code measured
Design Arena: agents building mobile apps11941143GLM 5.3
Design Arena: agents building Android appsNot measured1143Only Kimi K2.7 Code measured
Design Arena: agents building Godot gamesNot measured1147Only Kimi K2.7 Code measured
Design Arena: agents building gamesNot measured1130Only Kimi K2.7 Code measured
Design Arena: HTML slides11891201Kimi K2.7 Code
Design Arena: PowerPoint slides12551154GLM 5.3
LiveBench research73.2%Not measuredOnly GLM 5.3 measured
LiveBench browser0.0%Not measuredOnly GLM 5.3 measured
LiveBench long agentic35.9%Not measuredOnly GLM 5.3 measured
SREBench (Vals AI)9.2%Not measuredOnly GLM 5.3 measured
Finance Agent (Vals AI)55.8%Not measuredOnly GLM 5.3 measured
Tax Agent Bench (Vals AI)39.7%Not measuredOnly GLM 5.3 measured
Legal Research Bench (Vals AI)49.0%Not measuredOnly GLM 5.3 measured
Harvey's Legal Agent Benchmark (Vals AI)14.6%Not measuredOnly GLM 5.3 measured
Excel Modeling Benchmark (Vals AI)56.3%Not measuredOnly GLM 5.3 measured
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly GLM 5.3 measured
τ²-Bench TelecomNot measured90.1%Only Kimi K2.7 Code measured
APEX-Agents56.6%37.6%GLM 5.3
Vending-Bench 2$8,164$5,083GLM 5.3
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
Reasoning benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
GPQA Diamond88.1%Not measuredOnly GLM 5.3 measured
LiveBench reasoning85.8%Not measuredOnly GLM 5.3 measured
MysteryMechanism (Vals AI)23.0%Not measuredOnly GLM 5.3 measured
GPQA Diamond (Artificial Analysis run)91.7%89.6%GLM 5.3
Humanity's Last Exam (Artificial Analysis run)42.3%35.0%GLM 5.3
GPQA Diamond (Epoch AI run)90.9%87.9%GLM 5.3
SimpleBenchNot measured57.9%Only Kimi K2.7 Code measured
Chess puzzles37.0%14.0%GLM 5.3
Mystery game puzzles33.0%Not measuredOnly GLM 5.3 measured
LMArena Text: hard prompts1490Not measuredOnly GLM 5.3 measured
LMArena Text: expert1514Not measuredOnly GLM 5.3 measured
LMArena Text: hard prompts in English1496Not measuredOnly GLM 5.3 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index21
Math benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
OTIS Mock AIME91.1%95.6%Kimi K2.7 Code
FrontierMath, tiers 1 to 368.8%54.0%GLM 5.3
FrontierMath, tier 429.3%12.2%GLM 5.3
ProofBench49.0%Not measuredOnly GLM 5.3 measured
LMArena Text: math1495Not measuredOnly GLM 5.3 measured
LMArena Text: mathematical work1497Not measuredOnly GLM 5.3 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
MMLU Pro86.8%Not measuredOnly GLM 5.3 measured
LegalBench (Vals AI)84.8%Not measuredOnly GLM 5.3 measured
TaxEval (Vals AI)72.4%Not measuredOnly GLM 5.3 measured
MedCode (Vals AI)42.9%Not measuredOnly GLM 5.3 measured
SimpleQA Verified41.0%36.5%GLM 5.3
LMArena Text: science1498Not measuredOnly GLM 5.3 measured
LMArena Text: medicine and healthcare1481Not measuredOnly GLM 5.3 measured
LMArena Text: legal and government1473Not measuredOnly GLM 5.3 measured
LMArena Text: business and finance1459Not measuredOnly GLM 5.3 measured
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
Design Arena: websites12951264GLM 5.3
Design Arena: UI components13141259GLM 5.3
Design Arena: game dev13111220GLM 5.3
Design Arena: data viz12601226GLM 5.3
Design Arena: 3D13321241GLM 5.3
Design Arena: all code categories13041253GLM 5.3
Design Arena: SVG12921176GLM 5.3
Design Arena: ASCII art12131196GLM 5.3
LiveBench design77.3%Not measuredOnly GLM 5.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
General benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
Vals Index59.7%Not measuredOnly GLM 5.3 measured
LiveBench data analysis70.2%Not measuredOnly GLM 5.3 measured
Public Benefits Bench (Vals AI)68.5%Not measuredOnly GLM 5.3 measured
MedScribe (Vals AI)88.8%Not measuredOnly GLM 5.3 measured
IFBenchNot measured63.1%Only Kimi K2.7 Code measured
Long context reasoning (AA-LCR)79.7%79.3%GLM 5.3
DTBench87.7%Not measuredOnly GLM 5.3 measured
LMCA55.5%Not measuredOnly GLM 5.3 measured
Surface Evolver BenchNot measured48.8%Only Kimi K2.7 Code measured
LMArena Text1474Not measuredOnly GLM 5.3 measured
LMArena Text: instruction following1479Not measuredOnly GLM 5.3 measured
LMArena Text: creative writing1458Not measuredOnly GLM 5.3 measured
LMArena Text: English1482Not measuredOnly GLM 5.3 measured
LMArena Text: non-English1459Not measuredOnly GLM 5.3 measured
LMArena Text: Chinese1532Not measuredOnly GLM 5.3 measured
LMArena Text: German1488Not measuredOnly GLM 5.3 measured
LMArena Text: Japanese1460Not measuredOnly GLM 5.3 measured
LMArena Text: Korean1460Not measuredOnly GLM 5.3 measured
LMArena Text: French1503Not measuredOnly GLM 5.3 measured
LMArena Text: Spanish1462Not measuredOnly GLM 5.3 measured
LMArena Text: Russian1469Not measuredOnly GLM 5.3 measured
LMArena Text: Polish1466Not measuredOnly GLM 5.3 measured
LMArena Text: multi-turn1472Not measuredOnly GLM 5.3 measured
LMArena Text: longer queries1483Not measuredOnly GLM 5.3 measured
LMArena Text: writing and language1469Not measuredOnly GLM 5.3 measured
LMArena Text: entertainment and media1447Not measuredOnly GLM 5.3 measured
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5.3 and Kimi K2.7 Code
BenchmarkGLM 5.3Kimi K2.7 CodeLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GLM 5.3$0.0008Fits in one request
Kimi K2.7 Code$0.0023Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

GLM 5.3$0.0081Fits in one request
Kimi K2.7 Code$0.044Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

GLM 5.3$0.030Fits in one request
Kimi K2.7 Code$0.168Fits in one request

GLM 5.3 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GLM 5.3 and Kimi K2.7 Code
SpecificationZ.ai GLM 5.3MoonshotAI Kimi K2.7 Code
MakerZ.aiMoonshot AI
WeightsOpen weightsOpen weights
ReleasedAugust 18, 2026June 12, 2026
Context window1.05M262K
Input $/Mtok$0.079$0.6712
Output $/Mtok$1.40$3.35
Coding index73.139.1
Independent measurements behind it21
Cost per solved task$0.36$0.35
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.3 better than Kimi K2.7 Code for coding?

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 39.1 for Kimi K2.7 Code. Pick Kimi K2.7 Code when a solved task costs $0.35 against $0.36, or when what matters is LiveCodeBench (Vals AI) or SkillsBench (Vals AI), where it leads.

Which is cheaper, GLM 5.3 or Kimi K2.7 Code?

GLM 5.3 costs $0.079 per million input tokens and $1.40 per million output tokens; Kimi K2.7 Code costs $0.6712 and $3.35. Per solved SWE-bench Verified task, GLM 5.3 costs $0.36 and Kimi K2.7 Code $0.35.

Which has the bigger context window, GLM 5.3 or Kimi K2.7 Code?

GLM 5.3, with 1.05M tokens against 262K.

How many benchmarks is the GLM 5.3 vs Kimi K2.7 Code comparison based on?

40 benchmarks have a result for both models as of October 21, 2026. GLM 5.3's coding index rests on 2 independent benchmarks and Kimi K2.7 Code's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next